prompt listlengths 2 2 | label dict | metadata dict |
|---|---|---|
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "8",
"budget": 5786
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004125",
"normalized_example_id": "ex_004125",
"source_idx": 4125,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7232,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "8",
"budget": 7232
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004125",
"normalized_example_id": "ex_004125",
"source_idx": 4125,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7232,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\text{box 3}",
"budget": 6038
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004126",
"normalized_example_id": "ex_004126",
"source_idx": 4126,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 10063,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\text{box 3}",
"budget": 8050
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004126",
"normalized_example_id": "ex_004126",
"source_idx": 4126,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 10063,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\text{box 3}",
"budget": 10063
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004126",
"normalized_example_id": "ex_004126",
"source_idx": 4126,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 10063,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{9}{2}",
"budget": 1489
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004127",
"normalized_example_id": "ex_004127",
"source_idx": 4127,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2481,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{9}{2}",
"budget": 1985
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004127",
"normalized_example_id": "ex_004127",
"source_idx": 4127,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2481,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{9}{2}",
"budget": 2481
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004127",
"normalized_example_id": "ex_004127",
"source_idx": 4127,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2481,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "21,61,101,141",
"budget": 2341
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004129",
"normalized_example_id": "ex_004129",
"source_idx": 4129,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3901,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "21,61,101,141",
"budget": 3121
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004129",
"normalized_example_id": "ex_004129",
"source_idx": 4129,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3901,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "21,61,101,141",
"budget": 3901
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004129",
"normalized_example_id": "ex_004129",
"source_idx": 4129,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3901,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1018081",
"budget": 1861
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004131",
"normalized_example_id": "ex_004131",
"source_idx": 4131,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3101,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1018081",
"budget": 2481
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004131",
"normalized_example_id": "ex_004131",
"source_idx": 4131,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3101,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1018081",
"budget": 3101
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004131",
"normalized_example_id": "ex_004131",
"source_idx": 4131,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3101,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{10\\pi - 12\\sqrt{3}}{9}",
"budget": 5269
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004134",
"normalized_example_id": "ex_004134",
"source_idx": 4134,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8781,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{10\\pi - 12\\sqrt{3}}{9}",
"budget": 7025
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004134",
"normalized_example_id": "ex_004134",
"source_idx": 4134,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8781,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{10\\pi - 12\\sqrt{3}}{9}",
"budget": 8781
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004134",
"normalized_example_id": "ex_004134",
"source_idx": 4134,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8781,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{n(n+1)(n-1)(3n+2)}{24}",
"budget": 3383
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004137",
"normalized_example_id": "ex_004137",
"source_idx": 4137,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5638,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{n(n+1)(n-1)(3n+2)}{24}",
"budget": 4510
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004137",
"normalized_example_id": "ex_004137",
"source_idx": 4137,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5638,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{n(n+1)(n-1)(3n+2)}{24}",
"budget": 5638
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004137",
"normalized_example_id": "ex_004137",
"source_idx": 4137,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5638,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "67",
"budget": 4964
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004139",
"normalized_example_id": "ex_004139",
"source_idx": 4139,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8274,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "67",
"budget": 6619
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004139",
"normalized_example_id": "ex_004139",
"source_idx": 4139,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8274,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "67",
"budget": 8274
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004139",
"normalized_example_id": "ex_004139",
"source_idx": 4139,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8274,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "0",
"budget": 1189
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004141",
"normalized_example_id": "ex_004141",
"source_idx": 4141,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1981,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "0",
"budget": 1585
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004141",
"normalized_example_id": "ex_004141",
"source_idx": 4141,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1981,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "0",
"budget": 1981
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004141",
"normalized_example_id": "ex_004141",
"source_idx": 4141,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1981,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "8",
"budget": 1703
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004146",
"normalized_example_id": "ex_004146",
"source_idx": 4146,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2839,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "8",
"budget": 2271
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004146",
"normalized_example_id": "ex_004146",
"source_idx": 4146,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2839,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "8",
"budget": 2839
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004146",
"normalized_example_id": "ex_004146",
"source_idx": 4146,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2839,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "x = y = z = 2",
"budget": 4912
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004149",
"normalized_example_id": "ex_004149",
"source_idx": 4149,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8186,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "x = y = z = 2",
"budget": 6549
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004149",
"normalized_example_id": "ex_004149",
"source_idx": 4149,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8186,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "x = y = z = 2",
"budget": 8186
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004149",
"normalized_example_id": "ex_004149",
"source_idx": 4149,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8186,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "3^{6567340}",
"budget": 3020
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004151",
"normalized_example_id": "ex_004151",
"source_idx": 4151,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5033,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "3^{6567340}",
"budget": 4026
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004151",
"normalized_example_id": "ex_004151",
"source_idx": 4151,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5033,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "3^{6567340}",
"budget": 5033
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004151",
"normalized_example_id": "ex_004151",
"source_idx": 4151,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5033,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "4032",
"budget": 695
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004152",
"normalized_example_id": "ex_004152",
"source_idx": 4152,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1159,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "4032",
"budget": 927
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004152",
"normalized_example_id": "ex_004152",
"source_idx": 4152,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1159,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "4032",
"budget": 1159
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004152",
"normalized_example_id": "ex_004152",
"source_idx": 4152,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1159,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "625",
"budget": 3247
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004153",
"normalized_example_id": "ex_004153",
"source_idx": 4153,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5411,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "625",
"budget": 4329
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004153",
"normalized_example_id": "ex_004153",
"source_idx": 4153,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5411,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "625",
"budget": 5411
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004153",
"normalized_example_id": "ex_004153",
"source_idx": 4153,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5411,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{96}{41}",
"budget": 3662
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004156",
"normalized_example_id": "ex_004156",
"source_idx": 4156,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6103,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{96}{41}",
"budget": 4882
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004156",
"normalized_example_id": "ex_004156",
"source_idx": 4156,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6103,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{96}{41}",
"budget": 6103
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004156",
"normalized_example_id": "ex_004156",
"source_idx": 4156,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6103,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\pi",
"budget": 3243
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004158",
"normalized_example_id": "ex_004158",
"source_idx": 4158,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5405,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\pi",
"budget": 4324
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004158",
"normalized_example_id": "ex_004158",
"source_idx": 4158,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5405,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\pi",
"budget": 5405
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004158",
"normalized_example_id": "ex_004158",
"source_idx": 4158,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5405,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "4",
"budget": 881
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004159",
"normalized_example_id": "ex_004159",
"source_idx": 4159,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1468,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "4",
"budget": 1174
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004159",
"normalized_example_id": "ex_004159",
"source_idx": 4159,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1468,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "4",
"budget": 1468
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004159",
"normalized_example_id": "ex_004159",
"source_idx": 4159,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1468,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{2}{3}",
"budget": 688
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004160",
"normalized_example_id": "ex_004160",
"source_idx": 4160,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1146,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{2}{3}",
"budget": 917
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004160",
"normalized_example_id": "ex_004160",
"source_idx": 4160,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1146,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{2}{3}",
"budget": 1146
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004160",
"normalized_example_id": "ex_004160",
"source_idx": 4160,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1146,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "463",
"budget": 2117
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004164",
"normalized_example_id": "ex_004164",
"source_idx": 4164,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3528,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "463",
"budget": 2822
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004164",
"normalized_example_id": "ex_004164",
"source_idx": 4164,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3528,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "463",
"budget": 3528
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004164",
"normalized_example_id": "ex_004164",
"source_idx": 4164,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3528,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "Index",
"budget": 4012
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004166",
"normalized_example_id": "ex_004166",
"source_idx": 4166,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6686,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "Index",
"budget": 5349
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004166",
"normalized_example_id": "ex_004166",
"source_idx": 4166,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6686,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "Index",
"budget": 6686
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004166",
"normalized_example_id": "ex_004166",
"source_idx": 4166,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6686,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "143",
"budget": 1807
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004167",
"normalized_example_id": "ex_004167",
"source_idx": 4167,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3011,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "143",
"budget": 2409
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004167",
"normalized_example_id": "ex_004167",
"source_idx": 4167,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3011,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "143",
"budget": 3011
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004167",
"normalized_example_id": "ex_004167",
"source_idx": 4167,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3011,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{\\pi}{3}+\\frac{\\sqrt{3}}{2}",
"budget": 3102
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004169",
"normalized_example_id": "ex_004169",
"source_idx": 4169,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5170,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{\\pi}{3}+\\frac{\\sqrt{3}}{2}",
"budget": 4136
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004169",
"normalized_example_id": "ex_004169",
"source_idx": 4169,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5170,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{\\pi}{3}+\\frac{\\sqrt{3}}{2}",
"budget": 5170
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004169",
"normalized_example_id": "ex_004169",
"source_idx": 4169,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5170,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "27",
"budget": 4120
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004170",
"normalized_example_id": "ex_004170",
"source_idx": 4170,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6867,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "27",
"budget": 5494
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004170",
"normalized_example_id": "ex_004170",
"source_idx": 4170,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6867,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "27",
"budget": 6867
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004170",
"normalized_example_id": "ex_004170",
"source_idx": 4170,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6867,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "660",
"budget": 1368
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004173",
"normalized_example_id": "ex_004173",
"source_idx": 4173,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2280,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "660",
"budget": 1824
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004173",
"normalized_example_id": "ex_004173",
"source_idx": 4173,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2280,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "660",
"budget": 2280
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004173",
"normalized_example_id": "ex_004173",
"source_idx": 4173,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2280,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "0.49",
"budget": 2348
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004176",
"normalized_example_id": "ex_004176",
"source_idx": 4176,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3913,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "0.49",
"budget": 3130
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004176",
"normalized_example_id": "ex_004176",
"source_idx": 4176,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3913,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "0.49",
"budget": 3913
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004176",
"normalized_example_id": "ex_004176",
"source_idx": 4176,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3913,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "n \\equiv 1 \\pmod{3}",
"budget": 5785
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004178",
"normalized_example_id": "ex_004178",
"source_idx": 4178,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9641,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "n \\equiv 1 \\pmod{3}",
"budget": 7713
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004178",
"normalized_example_id": "ex_004178",
"source_idx": 4178,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9641,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "n \\equiv 1 \\pmod{3}",
"budget": 9641
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004178",
"normalized_example_id": "ex_004178",
"source_idx": 4178,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9641,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "f(n)=n^{3}",
"budget": 4318
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004180",
"normalized_example_id": "ex_004180",
"source_idx": 4180,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7196,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "f(n)=n^{3}",
"budget": 5757
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004180",
"normalized_example_id": "ex_004180",
"source_idx": 4180,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7196,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "f(n)=n^{3}",
"budget": 7196
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004180",
"normalized_example_id": "ex_004180",
"source_idx": 4180,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7196,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "27",
"budget": 1882
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004181",
"normalized_example_id": "ex_004181",
"source_idx": 4181,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3136,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "27",
"budget": 2509
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004181",
"normalized_example_id": "ex_004181",
"source_idx": 4181,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3136,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "27",
"budget": 3136
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004181",
"normalized_example_id": "ex_004181",
"source_idx": 4181,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3136,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "112",
"budget": 2098
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004182",
"normalized_example_id": "ex_004182",
"source_idx": 4182,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3497,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "112",
"budget": 2798
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004182",
"normalized_example_id": "ex_004182",
"source_idx": 4182,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3497,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "112",
"budget": 3497
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004182",
"normalized_example_id": "ex_004182",
"source_idx": 4182,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3497,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\sqrt{10}",
"budget": 1862
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004183",
"normalized_example_id": "ex_004183",
"source_idx": 4183,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3103,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\sqrt{10}",
"budget": 2482
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004183",
"normalized_example_id": "ex_004183",
"source_idx": 4183,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3103,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\sqrt{10}",
"budget": 3103
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004183",
"normalized_example_id": "ex_004183",
"source_idx": 4183,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3103,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "5\\pi",
"budget": 2586
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004184",
"normalized_example_id": "ex_004184",
"source_idx": 4184,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4310,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "5\\pi",
"budget": 3448
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004184",
"normalized_example_id": "ex_004184",
"source_idx": 4184,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4310,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "5\\pi",
"budget": 4310
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004184",
"normalized_example_id": "ex_004184",
"source_idx": 4184,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4310,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "a_{n}=\\frac{\\sqrt{3}+2}{2 \\sqrt{3}}(1+\\sqrt{3})^{n}+\\frac{\\sqrt{3}-2}{2 \\sqrt{3}}(1-\\sqrt{3})^{n}",
"budget": 4373
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004185",
"normalized_example_id": "ex_004185",
"source_idx": 4185,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7289,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "a_{n}=\\frac{\\sqrt{3}+2}{2 \\sqrt{3}}(1+\\sqrt{3})^{n}+\\frac{\\sqrt{3}-2}{2 \\sqrt{3}}(1-\\sqrt{3})^{n}",
"budget": 5831
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004185",
"normalized_example_id": "ex_004185",
"source_idx": 4185,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7289,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "a_{n}=\\frac{\\sqrt{3}+2}{2 \\sqrt{3}}(1+\\sqrt{3})^{n}+\\frac{\\sqrt{3}-2}{2 \\sqrt{3}}(1-\\sqrt{3})^{n}",
"budget": 7289
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004185",
"normalized_example_id": "ex_004185",
"source_idx": 4185,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7289,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "3",
"budget": 3413
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004186",
"normalized_example_id": "ex_004186",
"source_idx": 4186,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5689,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "3",
"budget": 4551
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004186",
"normalized_example_id": "ex_004186",
"source_idx": 4186,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5689,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "3",
"budget": 5689
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004186",
"normalized_example_id": "ex_004186",
"source_idx": 4186,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5689,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "(0,0,0,0)",
"budget": 2247
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004188",
"normalized_example_id": "ex_004188",
"source_idx": 4188,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3745,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "(0,0,0,0)",
"budget": 2996
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_004188",
"normalized_example_id": "ex_004188",
"source_idx": 4188,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3745,
... |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.